Energy Saving Strategy of UAV in MEC Based on Deep Reinforcement Learning

Zhiqiang Dai, Gaochao Xu, Ziqi Liu, Jiaqi Ge and Wei Wang
Additional contact information
Zhiqiang Dai: Department of Computer Science and Technology, Jilin University, Changchun 130012, China
Gaochao Xu: Department of Computer Science and Technology, Jilin University, Changchun 130012, China
Ziqi Liu: Department of Computer Science and Technology, Jilin University, Changchun 130012, China
Jiaqi Ge: Department of Computer Science and Technology, Jilin University, Changchun 130012, China
Wei Wang: Department of Computer Science and Technology, Jilin University, Changchun 130012, China

Future Internet, 2022, vol. 14, issue 8, 1-19

Abstract: Unmanned aerial vehicles (UAVs) have the characteristics of portability, safety, and strong adaptability. In the case of a maritime disaster, they can be used for personnel search and rescue, real-time monitoring, and disaster assessment. However, the power, computing power, and other resources of UAVs are often limited. Therefore, this paper combines a UAV and mobile edge computing (MEC), and designs a deep reinforcement learning-based online task offloading (DOTO) algorithm. The algorithm can obtain an online offloading strategy that maximizes the residual energy of the UAV by jointly optimizing the UAV’s time and communication resources. The DOTO algorithm adopts time division multiple access (TDMA) to offload and schedule the UAV computing task, integrates wireless power transfer (WPT) to supply power to the UAV, calculates the residual energy corresponding to the offloading action through the convex optimization method, and uses an adaptive K method to reduce the computational complexity of the algorithm. The simulation results show that the DOTO algorithm proposed in this paper for the energy-saving goal of maximizing the residual energy of UAVs in MEC can provide the UAV with an online task offloading strategy that is superior to other traditional benchmark schemes. In particular, when an individual UAV exits the system due to insufficient power or failure, or a new UAV is connected to the system, it can perform timely and automatic adjustment without manual participation, and has good stability and adaptability.

Keywords: UAV; MEC; TDMA; WPT; convex optimization; deep reinforcement learning (search for similar items in EconPapers)
JEL-codes: O3 (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
https://www.mdpi.com/1999-5903/14/8/226/pdf (application/pdf)
https://www.mdpi.com/1999-5903/14/8/226/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jftint:v:14:y:2022:i:8:p:226-:d:872248

Access Statistics for this article

Future Internet is currently edited by Ms. Grace You

More articles in Future Internet from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().